You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I test some non-photo content jpeg(2d drawing),
high FBCNNQF can preserve detail and noise,
but I notice some area have slight color(chroma) brightness change.
In this case, FBCNNQF 70 have slight brightness change on dark red area(red circle),
could you teach me how to improve color accurate for non-photo content?
Hello, thanks for the proposed issue! From my observation, the brightness change is hard to distinguish, maybe just because the restored image is cleaner so looks different. On the other hand, blind jpeg image restoration is inherently an inverse problem, which means that for the same content in a compressed image, it can come from different uncompressed image by setting different quality factors. To eliminate this ambiguity, we learn prior knowledge from training data, but there must be difference of data distribution between training and testing images. So if you want to have better results on anime images, the best way is to directly train or finetune the model with anime images (I only use DIV2K and Flickr2K as training data). Besides, anime images usually don't contain much high-frequency information, so it should be enough to use my pre-trained model with very small qf to remove artifacts.
maybe just because the restored image is cleaner so looks different.
That make sense, I think jpegchroma subsampling(420) and jpegq75,
create a lot of tiny chroma artifacts in this dark red area,
and jpegycbcr also have some issue for red color.
In my test, I think FBCNNQF 80~90 can let that dark red area restore better,
and current pre-trained model is really good for different content,
I plan implement input jpeg decode to uint16 and convert to float32 tensor,
result float32 convert uint16, and output png 16 bit depth,
maybe use high precision and reduce precision loss can let result better.
I think use libjxlButteraugli3-norm finetune model,
probably can improve FBCNN chroma performance.
Hello @jiaxi-jiang, Sorry to bother you,
I test some non-photo content jpeg(2d drawing),
high
FBCNN
QF
can preserve detail and noise,but I notice some area have slight color(chroma) brightness change.
In this case,
FBCNN
QF 70
have slight brightness change on dark red area(red circle),could you teach me how to improve color accurate for non-photo content?
original image (jpeg q75 420),
png 8 bit depth (
FBCNN
QF 70
)Other sample(QF 30,50,70)
The text was updated successfully, but these errors were encountered: